EP0411341A2 - Neural network - Google Patents
Neural network Download PDFInfo
- Publication number
- EP0411341A2 EP0411341A2 EP90112956A EP90112956A EP0411341A2 EP 0411341 A2 EP0411341 A2 EP 0411341A2 EP 90112956 A EP90112956 A EP 90112956A EP 90112956 A EP90112956 A EP 90112956A EP 0411341 A2 EP0411341 A2 EP 0411341A2
- Authority
- EP
- European Patent Office
- Prior art keywords
- neural
- inductance
- processing system
- outputting
- data processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
Definitions
- the present invention relates to a data processing system based on a concept of neural network.
- a neural network for such data processing system is organized by arranging neuron models (hereafter, called "neuron") 1 shown in Fig.11, in parallel as shown in Fig.12.
- Data D0 is output according to the comparison result between the sum of multiplied input data and threshold ⁇ .
- Data input from outside DI1, DI2, DI3,...DIn, are multiplied by weights W1, W2, W3,...Wn, respectively.
- Various comparison manners are possible. For example: it is determined that; an output data DO becomes “1" when the sum is more than or equal to threshold ⁇ , and an output data Do becomes "0" when said sum is smaller than threshold ⁇ .
- a neural network is constructed by connecting a neural layer in series, while the neural layer is constructed by arranging neurons in parallel.
- a neural network is constructed with 3 layers consisting of as many neurons as the number of data inputted.
- Macalloch - Pitts model handles normalized digital signal as an output, as shown in the following formula. ⁇ [ ( w i A i) - ⁇ ] where, ⁇ : normalizing function, wi: weight of i-th synapse, Ai: input to i-th synapse, ⁇ : threshold for neuron.
- the neural network disclosed in these issues have the structure to control by means of variable resistance inputs of operation amplifiers, each of which is connected to all other amplifiers in order to evaluate the energy formula below.
- the neural network suggested here is effective to calculate the minimum and maximum in variables given by the function equiv alent to the formula above. It is used to solve the problem of traveling salesman, for example.
- Such neural network lacks, however, the function to output digital value with normalization, that is, according to a compression with threshold. It cannot realize the function of neural network of organisms for information compression, integration and approximation. Therefore, the most advantageous characteristics of a neural network cannot be obtained by the above construction; that is, the improvement and associative convention of an input pattern cannot be performed.
- the present invention is invented so as to solve the above problems of the prior art and has an object to provide a data processing system capable of executing objective data processing without fail.
- the present invention has an object to provide a data processing system as an integrated circuit with a function of normalizing.
- a data processing system is characterized in that; the number of neural layers is equal to the number with respect to the abstraction difference between output data and input data, and at least 2 neural layers are divided into a plurality of neural cells which includes at least one neuron, and a neuron included in each neural cell is not connected to the neuron of other neural cell.
- a data processing system includes a resonance system for inputting which is connected to a switching circuit and is driven by a plurality of resonance systems for outputting. It realizes the function of normalization by the breaking performance of switching circuit.
- the data processing system consists of a plurality of neural cells NC each of which is formed into a hexa gon so that a honeycomb structure is constructed as a whole.
- an image is processed after it is divided into a plurality of unit areas.
- a unit area is square or rectangle area such as 3 x 3 pixels' area.
- the most preferable form of unit area is the one whose peripheral touches under equivalent conditions to adjacent unit areas.
- the honeycomb structure will provide the best processing condition by means of the above preference. It is possible to setup such preferable unit area, because the structure of neural layer can be set up independently from a hardware for scanning an image. According to the above, it is possible to optimize processing manner by setting up a unit area at neural network side rather than input system.
- a binary data is input to a data processing system through input system (not shown). As shown in Fig.1, a triangle figure F is input to the data processing system.
- Each neural cell is composed by a plurality of neural layers (Fig.2), each of which is constructed by arranging a plurality of neurons N in parallel.
- a structure of a neural cell is described in Fig.2.
- a neuron NR of each neural layer is connected with all neurons of an adjacent neural layer.
- Input data is processed by neural layers, successively, so as to obtain the final output, wherein the output of nth neural layer is the input of (n+1)th neural layer.
- Fig.3 schematically shows neural cells of neural layers 11, 12, 13 and 14 and typical relationship between a neural cell and the following neural layer 20.
- each of neural layers 11, 12, 13 and 14 is divided into hexagonal neural cells NC.
- a neural cell includes a plurality of neural layers 11, 12, 13 and 14, and a large number of neurons are included in each neural layer. Neurons are connected with one another only within a neural cell and neurons belonging to another neural cells are never connected with each other. According to the above, each neural cell NC is not connected with each other so that data transmission is only performed inside each neural cell, individually. It is also possible to construct a neural cell. Preparing of a neural cell NC for 2 neural layers is acceptable.
- a data processing system is able to furnish with the objective processing function by learning.
- performance of simple recognition of geometrical figure is described.
- FIG.4 An embodiment of a neural layer for the performance of edge extraction is shown in Fig.4.
- Neurons A to I corresponding to 3x3 convolution are shown in Fig.4, in which neuron outputs "1" with respect to the input with high brightness value.
- Outputs A to I are input to neuron N1, and outputs A to D, and F to I are input to neuron N2. Then, outputs from neuron N1 and N2 are input to neuron N3.
- weights for neuron N1 to N3 and thresholds are set up as shown in Table 1 to 3, as one example.
- neuron N1 performs the processing according to; E ( A + B + C + D + F + G + H + I ) (2)
- Neuron N2 performs the processing according to; A + B + C + D + F + G + H + I (3)
- neuron N3 performs the processing according to AND logic of above formulas (2) and (3).
- neuron N3 outputs "1" when the edge of a configuration is projected to neuron E.
- Fig.5 input of this neural network is an output of neuron N3 of Fig.4.
- neuron N3 according to neuron A to I is expressed as A′ to I′.
- Neurons N401 to N424 and N425 are prepared for this processing.
- Output A′ to D′ and F′ to I′ are input to neuron N401 to N424 with respect to the combinations shown in Table 4, and weights and threshold for the above input are shown as follows: Table 4 Neuron Weight Input Threshold N401 A′,B′ 1 1.5 N402 A′,C′ 1 1.5 N403 A′,D′ 1 1.5 N404 A′,F′ 1 1.5 N405 A′,G′ 1 1.5 N406 A′,H′ 1 1.5 N407 B′,C′ 1 1.5 N408 B′,D′ 1 1.5 N409 B′,F′ 1 1.5 N410 B′,G′ 1 1.5 N411 B′,I′ 1 1.5 N412 C′,D′ 1 1.5 N413 C′,F′ 1 1.5 N414 C′,H′ 1 1.5 N415 C′,I′ 1 1.5 N416 D′,G′ 1 1.5 N417 D′,H′ 1 1.5 N418 D′,
- Outputs N401 to N424 are input to N425, and weight and threshold for the above are shown in Table 5.
- Table 5 Neuron Weight Threshold N401 ⁇ N424 1 1.5
- neuron N245 and E′ are input to neuron N246, and weight and threshold for the above are shown in Table 6.
- Table 6 Neuron Weight Threshold N245 1 1.5 E 1
- a high neuron efficiency can be obtained by an advanced artificial setup of layer in which each data is input.
- a neural network with the same functions as Fig.4 can be constructed(Fig.6) by inputting of data E′ to the first neural layer, together with A′ to D′ and F′ to I′, according to the neural network in Fig.5.
- Fig.6 a neural network with the same functions as Fig.4
- Fig.6 a neural network with the same functions as Fig.6
- Fig.6 a neural network with the same functions as Fig.6
- Neural layer group INT is composed with plural processing systems P1 to Pn, and each process system is constructed with plural number of neural layers. Processing systems P1 to Pn are classified by the shape of a configuration, for example; P1: triangle, P2: rectangle, Pn: a polygon with (n+2) corners.
- Output from said neural cell is the signal showing of existence of edges(hereinafter called “ES") and corners(hereinafter called “CS") inside the neural cell.
- ES edges
- CS corners
- Neurons corresponding to said neural cell are included in the neural network in Fig.9. Each neuron is connected to all neural cell NC as neuron 21 in Fig.3. Weight of each neuron is; the maximal as compared with input of corresponding neural cell CS, the negative weight whose absolute value is the largest as compared with neural cell surrounding to corresponding neural cell, heightened its weight as the distance from corresponding neural cell becomes larger. The above relationship is described in Fig.10 by the second dimensions.
- corner signal of appeared pseudo-corner during the processing is weakened, and corner signal of corner A, B and C is enhanced.
- the graph in Fig.10 shows the approximation curve of a second degree indicating the relationship between distance and weight. Needless to say, adaptation of a monotonous increasing curve is also possible.
- a data to be given to each processing system of neural layer INT is an abstracted data at neural cell and can be said that is a data at high degree. It is possible to input data to input data to neural layer group INT, directly, when the image processing system, enable of extracting corner and edge data, is used as an input system. It is possible to heightened the neuron efficiency by inputting data at high degree, corner for example, to the neural layer at following column, when image data and characteristics data, corner for example, is confused. It is possible to calculate the minimum number of neural layers so as to achieve expected objective results, by calculating the difference of the degrees between final data to be output and first data to be input to neural layer.
- the data processing system has the basic unit of the circuit shown in Fig. 13.
- the circuit in Fig. 13 comprises normalizing circuit 101, closed circuits for outputting 102 and 102′.
- Normalizing circuit 101 is a resonance system, comprising a closed circuit 103 for inputting, inductance L1 for inputting, capacitance CI for outputting and resistance RI.
- Induced electromotive force EI is generated in closed circuit 103 for inputting by mutual inducing action between closed circuit 103 and closed circuit 102.
- Capacitance CI for outputting is charged by induced current II generated by the induced electromotive force EI in closed circuit 103: consequently, potential difference is generated on opposite terminals of CI.
- Switching circuit 4 includes a transistor TR, whose base and corrector are connected to opposite terminals of capacitance CI, respectively. When a forward voltage Vbe between a base and emitter of the transistor TR exceeds the breaking range of TR, TR becomes conductive. A collector voltage Vcc is loaded on the collector of TR, the emitter of transistor TR is earthed through inductance 105 for outputting.
- Closed circuit 103 for inputting and transistor TR are connected with each other through diodes D1 and D2 which have the function of commutation in forward direction so as to prevent the transistor TR from reversed bias.
- diodes D1 and D2 which have the function of commutation in forward direction so as to prevent the transistor TR from reversed bias.
- emitter current Ie is generated, which flows through inductance 105 for output.
- Inductance 105 is connected magnetically with a plurality of closed circuit 102′ for outputting. Induced electromotive force EO is generated in each closed circuit 102′ by mutual inducing action between inductance 105 and each closed circuit 102′.
- closed circuits 102 and 102′ comprise inductance LOI for inputting, inductance LOO for outputting and variable resistance r.
- the induced electromotive force EO is generated by mutual inducing between inductance LOI for inputting and inductance LO for outputting of normalizing circuit 1.
- Output current IO is generated by the induced electromotive force EO in closed circuit 102′ for outputting: simultaneously, the induced electromotive force EI is generated by mutual inducing action between inductance LOO for outputting and inductance LI for inputting in closed circuit 101 for inputting 1.
- Potential difference Vci generated in capacitance CI by induced electromotive force EO is as follows.
- Vci 1 CI ⁇ IIdt (1)
- the electromotive force generated in each closed circuit 102 for output is assumed to be Vi (i is from 1 to n), and Vi is assumed as in formula (2).
- Vi Voi sin( ⁇ t+Si) (2) where, ⁇ is the resonance angle frequency common to all closed circuits 102 band 102′ for outputting and closed circuit 103 for inputting. That is, all closed circuits have the common resonance frequency. The attenuation is minimized, during the transmission of electrical signal from closed circuit 103 for outputting to normalizing circuit 1 and the transmission of electrical signal form normalizing circuit 101 to closed circuit 102′ for outputting, because of the common resonance frequency.
- Induced electromotive force EI in closed circuit 103 for inputting is expressed in formula (6), assuming that the mutual inductance is M between inductance LOO for outputting in closed circuit 102 for outputting and inductance LI for inputting in closed circuit 103 for inputting, and assuming that ⁇ equal to Co ⁇ o ⁇ o (Co is light speed in vacuum, ⁇ o is dielectric constant in vacuum of rational units, ⁇ o is magnetic permeability in vacuum of rational units). Therefore, the current shown below is generated in closed circuit for inputting. Substituting (9) into (1), formula (10) is obtained. Accordingly, Vbe is expressed as in formula (11).
- Fig. 16 is a diagram showing induced electromotive force Eo by generated emitter current in Fig. 15.
- normalized circuit 101 can execute threshold processing based on switching characteristics. As shown in Fig. 17, any outputs of normalizing circuit 101 can be inputted to other normalizing circuits 101′ by closed circuit 102 (102′) for outputting, and simultaneously, the outputs of other normalizing circuits 101 ⁇ can be inputted to a normalizing circuit 101 by closed circuit 102 (102′) for outputting. Therefore, network can be regenerated, and it is possible to settle a weight of synapse in the network by adjusting variable resister r in closed circuit 102 (102′) for outputting.
- insulator 108 is formed, which performs as:
- Insulator 110 performs as:
- the data processing system has; advantages of efficiency as well as faculty to achieve expected objective results, since the number of neural layers is equal to the number corresponding to the abstraction difference between output data and input data, the structure of at least 2 neural layers are divided into a plurality of neural cells each of which includes at least one neuron, and a neuron included in each neural cell is not connected to the neuron of other neural cells; therefore, a predetermined processing is certainly performed because heterogeneous data are never processed in one neural cell but processed in parallel and independently from one another.
- data processing system drives the resonance system for inputting connected to switching circuit by which the resonance system for outputting is driven. It is possible to possess the number of neurons for practicing, since it is possible to realize neural network with the function of normalization by analog circuit.
Abstract
Description
- The present invention relates to a data processing system based on a concept of neural network.
- A neural network for such data processing system is organized by arranging neuron models (hereafter, called "neuron") 1 shown in Fig.11, in parallel as shown in Fig.12.
- Data D0 is output according to the comparison result between the sum of multiplied input data and threshold ϑ . Data input from outside DI1, DI2, DI3,...DIn, are multiplied by weights W1, W2, W3,...Wn, respectively. Various comparison manners are possible. For example: it is determined that;
an output data DO becomes "1" when the sum is more than or equal to threshold ϑ, and
an output data Do becomes "0" when said sum is smaller than threshold ϑ. - A neural network is constructed by connecting a neural layer in series, while the neural layer is constructed by arranging neurons in parallel. Conventionally, there was not established theory for the construction of neural network. Usually, following to perceptron proposed by Rosenblatt, a neural network is constructed with 3 layers consisting of as many neurons as the number of data inputted.
- Therefore, it has never been clarified the correlation between data processing to be performed by a neural network and the structure of the neural network. The evaluation cannot be made whether constructed neural network can accomplish expected object or not, until the neural network is experimented.
- As for a neuron which is the component of the neural network, it is not so difficult to realize Macalloch - Pitts model by a digital circuit. Macalloch - Pitts model handles normalized digital signal as an output, as shown in the following formula.
φ[ ( w i A i) -ϑ]
where, φ: normalizing function,
wi: weight of i-th synapse,
Ai: input to i-th synapse,
ϑ: threshold for neuron. - However, rather large circuits are necessary for the calculation including multiplications, so it is difficult to construct a large scale neural network due to circuitry limit of ICs.
- It is suggested an attempt to construct neural network by analog circuit in United States Patent No. 4,660,166, No. 4,719,591 and No. 4,731,747.
-
- The neural network suggested here is effective to calculate the minimum and maximum in variables given by the function equiv alent to the formula above. It is used to solve the problem of traveling salesman, for example.
- Such neural network lacks, however, the function to output digital value with normalization, that is, according to a compression with threshold. It cannot realize the function of neural network of organisms for information compression, integration and approximation. Therefore, the most advantageous characteristics of a neural network cannot be obtained by the above construction; that is, the improvement and associative convention of an input pattern cannot be performed.
- The present invention is invented so as to solve the above problems of the prior art and has an object to provide a data processing system capable of executing objective data processing without fail.
- The present invention has an object to provide a data processing system as an integrated circuit with a function of normalizing.
- A data processing system according to the present invention is characterized in that;
the number of neural layers is equal to the number with respect to the abstraction difference between output data and input data, and
at least 2 neural layers are divided into a plurality of neural cells which includes at least one neuron, and a neuron included in each neural cell is not connected to the neuron of other neural cell. - A data processing system according to the present invention includes a resonance system for inputting which is connected to a switching circuit and is driven by a plurality of resonance systems for outputting. It realizes the function of normalization by the breaking performance of switching circuit.
-
- Fig.1 shows a schematic diagram of an embodiment of a data processing system including neural cells, according to the present invention;
- Fig.2 shows a schematic diagram including layers of above neural cell;
- Fig.3 shows a schematic diagram indicating the structure of a neural cell and the structure of a neural layer for the following processing;
- Fig.4 shows a schematic diagram indicating the edge extraction processing system according to the above neural cell;
- Fig.5 shows a schematic diagram indicating the corner extraction processing system according to the above neural cell;
- Fig.6 shows a schematic diagram indicating the example of the transformation of Fig.4;
- Fig.7 shows a schematic diagram indicating a synthetic processing system at following column of neural processing system;
- Fig.8 shows a schematic diagram indicating a pseudo-corner of a configuration;
- Fig.9 shows a schematic diagram indicating the relationship between neurons by the second dimensional location;
- Fig.10 shows a graph indicating the relationship between neurons by distance and weight;
- Fig.11 shows a schematic diagram indicating neuron model;
- Fig.12 shows a schematic diagram indicating the example of neural layer;
- Fig.13 shows the circuit with the structure of basic unit in the first embodiment of a data processing system according to the present invention;
- Fig.14 is a diagram showing voltage between base and emitter of transistor in the first embodiment;
- Fig.15 is a diagram showing current of emitter of transistor in the first embodiment;
- Fig.16 is a diagram showing induced electromotive force of closed circuit for outputting in the first embodiment;
- Fig.17 is a diagram showing a connection of normalizing circuits;
- Fig.18 is a perspective view of inductance in an IC;
- Fig.19 is a perspective view of another inductance;
- Fig.20 shows a circuit of a form of changeable resistance in and IC.
- Hereinafter, an embodiment of the data processing system according to the present invention is described with referring to the attached drawings.
- As shown in Fig.1, the data processing system consists of a plurality of neural cells NC each of which is formed into a hexa gon so that a honeycomb structure is constructed as a whole.
- In general, an image is processed after it is divided into a plurality of unit areas. Here, a unit area is square or rectangle area such as 3 x 3 pixels' area. Although the form of above unit area is resulted from such performance of a hardware that an image is scanned along horizontal scan lines. The most preferable form of unit area is the one whose peripheral touches under equivalent conditions to adjacent unit areas. The honeycomb structure will provide the best processing condition by means of the above preference. It is possible to setup such preferable unit area, because the structure of neural layer can be set up independently from a hardware for scanning an image. According to the above, it is possible to optimize processing manner by setting up a unit area at neural network side rather than input system.
- A binary data is input to a data processing system through input system (not shown). As shown in Fig.1, a triangle figure F is input to the data processing system.
- Each neural cell is composed by a plurality of neural layers (Fig.2), each of which is constructed by arranging a plurality of neurons N in parallel. A structure of a neural cell is described in Fig.2. According to the above embodiment, a neuron NR of each neural layer is connected with all neurons of an adjacent neural layer. Input data is processed by neural layers, successively, so as to obtain the final output, wherein the output of nth neural layer is the input of (n+1)th neural layer. Fig.3 schematically shows neural cells of neural layers 11, 12, 13 and 14 and typical relationship between a neural cell and the following
neural layer 20. In Fig.3 each of neural layers 11, 12, 13 and 14 is divided into hexagonal neural cells NC. That is, a neural cell includes a plurality of neural layers 11, 12, 13 and 14, and a large number of neurons are included in each neural layer. Neurons are connected with one another only within a neural cell and neurons belonging to another neural cells are never connected with each other. According to the above, each neural cell NC is not connected with each other so that data transmission is only performed inside each neural cell, individually. It is also possible to construct a neural cell. Preparing of a neural cell NC for 2 neural layers is acceptable. - A data processing system is able to furnish with the objective processing function by learning. Hereinafter, performance of simple recognition of geometrical figure is described.
- An embodiment of a neural layer for the performance of edge extraction is shown in Fig.4. Neurons A to I corresponding to 3x3 convolution are shown in Fig.4, in which neuron outputs "1" with respect to the input with high brightness value. When outputs of neurons A to I are deemed to be A to I, existence of edges except isolate points can be described by logical formula as follows:
E(A +B +C +D +F+G +H +I )(A+B+C+D+F+G+H+I)= 1 (1) - Outputs A to I are input to neuron N1, and outputs A to D, and F to I are input to neuron N2. Then, outputs from neuron N1 and N2 are input to neuron N3. Here, weights for neuron N1 to N3 and thresholds are set up as shown in Table 1 to 3, as one example.
Table 1 Weight and threshold for neuron N1 Weight with respect to output A W1A -1 Weight with respect to output B W1B -1 Weight with respect to output C W1C -1 Weight with respect to output D W1D -1 Weight with respect to output E W1E 9 Weight with respect to output F W1F -1 Weight with respect to output G W1G -1 Weight with respect to output H W1H -1 Weight with respect to output I W1I -1 Theshold ϑ1 0.5 Table 2 Weight and threshold for neuron N2 Weight with respect to output A W2A 1 Weight with respect to output B W2B 1 Weight with respect to output C W2C 1 Weight with respect to output D W2D 1 Weight with respect to output E W2E 1 Weight with respect to output F W2F 1 Weight with respect to output G W2G 1 Weight with respect to output H W2H 1 Weight with respect to output I W2I 1 Theshold ϑ2 0.5 Table 3 Weight and threshold for neuron N3 Weight with respect ot output N1 W3N1 1 Weight with respect to output N2 W2N2 1 Threshold ϑ 1.5 - Here, neuron N1 performs the processing according to; E (
A +B +C +D +F +G +H +I ) (2) - Neuron N2 performs the processing according to; A + B + C + D + F + G + H + I (3)
- On the other hand, neuron N3 performs the processing according to AND logic of above formulas (2) and (3).
- Therefore, neuron N3 outputs "1" when the edge of a configuration is projected to neuron E.
- Hereinafter, an neural network which performs corner extraction is described according to Fig.5. Here, input of this neural network is an output of neuron N3 of Fig.4. In Fig.5, neuron N3 according to neuron A to I is expressed as A′ to I′. The logic formula (4) for extracting the corner is shown as follows:
E′ (A′ B′ +A′ C′ +A′ D′ +A′ F′ +A′ G′ +A′ H′ +B′ C′ +B′ D′ +B′ F′ +B′ G′ +B′ I′ +C′ D′ + C′ F′ +C′ H′ +C′ I′ +D′ G′ +D′ H′ +D′ I′ +F′ G′ +F′ H′ +F′ I′ +G′ H′ +G′ I′ +H′ I′ ) = 1 (4) - Neurons N401 to N424 and N425 are prepared for this processing. Output A′ to D′ and F′ to I′ are input to neuron N401 to N424 with respect to the combinations shown in Table 4, and weights and threshold for the above input are shown as follows:
Table 4 Neuron Weight Input Threshold N401 A′,B′ 1 1.5 N402 A′,C′ 1 1.5 N403 A′,D′ 1 1.5 N404 A′,F′ 1 1.5 N405 A′,G′ 1 1.5 N406 A′,H′ 1 1.5 N407 B′,C′ 1 1.5 N408 B′,D′ 1 1.5 N409 B′,F′ 1 1.5 N410 B′,G′ 1 1.5 N411 B′,I′ 1 1.5 N412 C′,D′ 1 1.5 N413 C′,F′ 1 1.5 N414 C′,H′ 1 1.5 N415 C′,I′ 1 1.5 N416 D′,G′ 1 1.5 N417 D′,H′ 1 1.5 N418 D′,I′ 1 1.5 N419 F′,G′ 1 1.5 N420 F′,H′ 1 1.5 N421 F′,I′ 1 1.5 N422 G′,H′ 1 1.5 N423 G′,I′ 1 1.5 N424 H′,I′ 1 1.5 - Outputs N401 to N424 are input to N425, and weight and threshold for the above are shown in Table 5.
Table 5 Neuron Weight Threshold N401 ∼ N424 1 1.5 - This is equivalent to OR logic.
- Furthermore, output of neuron N245 and E′ are input to neuron N246, and weight and threshold for the above are shown in Table 6.
Table 6 Neuron Weight Threshold N245 1 1.5 E 1 - This is equivalent to AND logic.
- Although setup of above weight is automatically performed by learning of a data processing system and optimized association can be obtained by appropriate learning, a high neuron efficiency can be obtained by an advanced artificial setup of layer in which each data is input. For example, a neural network with the same functions as Fig.4 can be constructed(Fig.6) by inputting of data E′ to the first neural layer, together with A′ to D′ and F′ to I′, according to the neural network in Fig.5. In this case, it is possible to reduce the number of layers by 1; however, extreme increase in number of connection lines, contrary to the above, as to increase the number of synapses of the first neural layer by 24. Since input E′ according to the formula (4), is affected with respect to the result of logic operation (A′ B′ + ...), input E′ is considered to have the abstraction ratio at the same level of that of the result inside the parenthesis. Therefore, neuron efficiency can be improved by inputting layers corresponding to this abstraction ratio.
- Here, the concept of degree according to abstraction ratio of data is implemented and following definitions are taken into the consideration:
- 1. By a processing of a single neural layer, degree is heightened by 1.
- 2. An input to the same neural layer is the one at the same degree.
- According to the above definitions, 4 layers(in the case when the constructions in Fig.4 and Fig.6 are adapted) or 5 layers(in the case when the constructions in Fig.4 and Fig.5 are adapted) are necessary for corner extraction, and the degree of the final output becomes 4 or 5 degrees when degree of image data (the input to neurons A to I) is deemed to be 0.
- The determination is output whether corners and edges for each neural cell are extracted or not, according to the above processing. As shown in Fig.7, this determination output is input to neural layer group INT for the unification. Data to be processed at this neural layer group INT is the one at higher degree and said neural layer. Neural layer group INT is composed with plural processing systems P1 to Pn, and each process system is constructed with plural number of neural layers. Processing systems P1 to Pn are classified by the shape of a configuration, for example; P1: triangle, P2: rectangle, Pn: a polygon with (n+2) corners.
- Output from said neural cell is the signal showing of existence of edges(hereinafter called "ES") and corners(hereinafter called "CS") inside the neural cell. There is the case when pseudo-corner X1 or X2 is appeared at side of a configuration as shown in Fig.8, due to the noises or tolerance of the configuration itself, even though it is a single triangle.
- According to the processing system for a triangle, such failed corner signal is removed and actual corner A, B and C are enhanced, so as to output the coordinate values. An embodiment of a neural network which performs the enhancement of corner A, B and C and the removal of the pseudo-corner is shown in Fig.9.
- Neurons corresponding to said neural cell are included in the neural network in Fig.9. Each neuron is connected to all neural cell NC as
neuron 21 in Fig.3. Weight of each neuron is;
the maximal as compared with input of corresponding neural cell CS,
the negative weight whose absolute value is the largest as compared with neural cell surrounding to corresponding neural cell,
heightened its weight as the distance from corresponding neural cell becomes larger. The above relationship is described in Fig.10 by the second dimensions. - According to the above structure, corner signal of appeared pseudo-corner during the processing is weakened, and corner signal of corner A, B and C is enhanced. The graph in Fig.10 shows the approximation curve of a second degree indicating the relationship between distance and weight. Needless to say, adaptation of a monotonous increasing curve is also possible.
- According to Perceptrons introduced by Rosenblatt, the structure for the performance of edge enhancement of ignition pattern is proposed, by giving the control-type-connection to feed back system from reaction layer to integration layer. However, there is no suggestion whatsoever, with regards to feed forward control-type-connection for the corner enhancement of specific configuration.
- A data to be given to each processing system of neural layer INT is an abstracted data at neural cell and can be said that is a data at high degree. It is possible to input data to input data to neural layer group INT, directly, when the image processing system, enable of extracting corner and edge data, is used as an input system. It is possible to heightened the neuron efficiency by inputting data at high degree, corner for example, to the neural layer at following column, when image data and characteristics data, corner for example, is confused. It is possible to calculate the minimum number of neural layers so as to achieve expected objective results, by calculating the difference of the degrees between final data to be output and first data to be input to neural layer.
- Therefore, the present invention has advantages below.
- (1) A predetermined processing is certainly performed according to the following assumption; the higher the abstraction of output data is, the more the number of neural layer becomes.
- (2) Each neural cell is divided and data to be input to neural cell is output after it is processed in parallel; that is data is processed independently on after another. Therefore, a predetermined processing is certainly performed due to the fact that a heterogeneous data is never processed by processing system since input data according to a data processing system is processed individually after being classified with respect to the sorts or the character.
- Hereinafter, an embodiment of the data processing system according to the present invention is described with referring to the attached drawings. The data processing system has the basic unit of the circuit shown in Fig. 13. The circuit in Fig. 13 comprises normalizing
circuit 101, closed circuits for outputting 102 and 102′. Normalizingcircuit 101 is a resonance system, comprising aclosed circuit 103 for inputting, inductance L1 for inputting, capacitance CI for outputting and resistance RI. Induced electromotive force EI is generated inclosed circuit 103 for inputting by mutual inducing action betweenclosed circuit 103 andclosed circuit 102. Capacitance CI for outputting is charged by induced current II generated by the induced electromotive force EI in closed circuit 103: consequently, potential difference is generated on opposite terminals of CI.Switching circuit 4 includes a transistor TR, whose base and corrector are connected to opposite terminals of capacitance CI, respectively. When a forward voltage Vbe between a base and emitter of the transistor TR exceeds the breaking range of TR, TR becomes conductive. A collector voltage Vcc is loaded on the collector of TR, the emitter of transistor TR is earthed throughinductance 105 for outputting.Closed circuit 103 for inputting and transistor TR are connected with each other through diodes D1 and D2 which have the function of commutation in forward direction so as to prevent the transistor TR from reversed bias. When transistor TR is conductive, emitter current Ie is generated, which flows throughinductance 105 for output. -
Inductance 105 is connected magnetically with a plurality ofclosed circuit 102′ for outputting. Induced electromotive force EO is generated in eachclosed circuit 102′ by mutual inducing action betweeninductance 105 and eachclosed circuit 102′. - As shown in Fig. 14,
closed circuits circuit 1. Output current IO is generated by the induced electromotive force EO inclosed circuit 102′ for outputting: simultaneously, the induced electromotive force EI is generated by mutual inducing action between inductance LOO for outputting and inductance LI for inputting inclosed circuit 101 for inputting 1. Potential difference Vci generated in capacitance CI by induced electromotive force EO is as follows.
Vci=
The electromotive force generated in eachclosed circuit 102 for output is assumed to be Vi (i is from 1 to n), and Vi is assumed as in formula (2).
Vi= Voi sin(ωt+Si) (2)
where, ω is the resonance angle frequency common to allclosed circuits 102band 102′ for outputting andclosed circuit 103 for inputting. That is, all closed circuits have the common resonance frequency. The attenuation is minimized, during the transmission of electrical signal fromclosed circuit 103 for outputting to normalizingcircuit 1 and the transmission of electrical signalform normalizing circuit 101 to closedcircuit 102′ for outputting, because of the common resonance frequency. Assuming the resistance value of variable resistance r in i-th closed circuit for outputting 2 to be ri, the current IOi generated in the closed circuit for outputting can be calculated from formula (2), then the formulae below can be obtained.r i² + ω²(L O I + LOO)² } sin (ω t -ϑ i) (4)
ϑ i =-tan⁻¹ {ω (L O I + L O O)/r i} (5) - Induced electromotive force EI in
closed circuit 103 for inputting is expressed in formula (6), assuming that the mutual inductance is M between inductance LOO for outputting inclosed circuit 102 for outputting and inductance LI for inputting inclosed circuit 103 for inputting, and assuming that Γ equal to Co εo µo (Co is light speed in vacuum, εo is dielectric constant in vacuum of rational units, µo is magnetic permeability in vacuum of rational units). - Supposing that Vbe has a characteristics shown in Fig. 14 (solid line) and that the breaking range of transistor TR is the level of broken line in Fig. 14, emitter current Ie is generated only when Vbe exceeds the broken line as shown in Fig. 15.
-
- As described above, normalized
circuit 101 can execute threshold processing based on switching characteristics. As shown in Fig. 17, any outputs of normalizingcircuit 101 can be inputted to other normalizingcircuits 101′ by closed circuit 102 (102′) for outputting, and simultaneously, the outputs of other normalizingcircuits 101˝ can be inputted to a normalizingcircuit 101 by closed circuit 102 (102′) for outputting. Therefore, network can be regenerated, and it is possible to settle a weight of synapse in the network by adjusting variable resister r in closed circuit 102 (102′) for outputting. - When inductances are constructed in IC of normalizing
circuit 1 andclosed circuits - In Fig. 18,
insulator 108 is formed, which performs as: - i) Forming
spiral conductor 106 on thefirst insulator 105, and - ii) Penetrating the
first insulator 105 from the center ofconductor 106, throughinsulator 105, pass thesecond insulator 107 and back again on thefirst insulator 105. - Current can be generated in
insulator 106 and inductance can be realized by such structure. - In Fig. 107,
insulator 110 andhooked insulator 111 are formed.Insulator 110 performs as: - i) Forming hooked
conductor 109 on the first insulator 5, - ii) Penetrating the
first insulator 105 from and end ofconductor 109, throughinsulator 105, reach thesecond insulator 107. - As mentioned above, the data processing system according to the present invention has;
advantages of efficiency as well as faculty to achieve expected objective results, since the number of neural layers is equal to the number corresponding to the abstraction difference between output data and input data,
the structure of at least 2 neural layers are divided into a plurality of neural cells each of which includes at least one neuron, and a neuron included in each neural cell is not connected to the neuron of other neural cells; therefore, a predetermined processing is certainly performed because heterogeneous data are never processed in one neural cell but processed in parallel and independently from one another. - Furthermore, data processing system according to the present invention drives the resonance system for inputting connected to switching circuit by which the resonance system for outputting is driven. It is possible to possess the number of neurons for practicing, since it is possible to realize neural network with the function of normalization by analog circuit.
Claims (9)
A plurality of normalizing circuits which comprises;
A closed circuit for inputting including an inductance for inputting and a capacitance for outputting, a switching circuit driven by a potential difference of said capacitance for outputting, and an inductance for outputting energized when said switching circuit is closed; and
A plurality of closed circuits for outputting which comprises a variable resistance, an inductance for inputting and an inductance for outputting has a resonance frequency substantially equal to that of said closed circuit for inputting, said inductance for outputting in said normalizing circuits being magnetically connected with said inductance for inputting in said closed circuit, and said inductance for outputting in said closed circuits for outputting being connected with said inductance for inputting in one of said normalizing circuit.
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP178377/89 | 1989-07-10 | ||
JP17837789 | 1989-07-10 | ||
JP20722089 | 1989-08-10 | ||
JP207220/89 | 1989-08-10 |
Publications (2)
Publication Number | Publication Date |
---|---|
EP0411341A2 true EP0411341A2 (en) | 1991-02-06 |
EP0411341A3 EP0411341A3 (en) | 1992-05-13 |
Family
ID=26498563
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP19900112956 Withdrawn EP0411341A3 (en) | 1989-07-10 | 1990-07-06 | Neural network |
Country Status (3)
Country | Link |
---|---|
US (2) | US5463717A (en) |
EP (1) | EP0411341A3 (en) |
KR (1) | KR910003516A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0443208A2 (en) * | 1990-02-20 | 1991-08-28 | Kabushiki Kaisha Wacom | Inductively coupled neural network |
US5297232A (en) * | 1991-10-30 | 1994-03-22 | Westinghouse Electric Corp. | Wireless neural network and a wireless neural processing element |
US5371835A (en) * | 1990-02-02 | 1994-12-06 | Kabushikikaisha Wacom | Inductively coupled neural network |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002358523A (en) * | 2001-05-31 | 2002-12-13 | Canon Inc | Device and method for recognizing and processing pattern, and image input device |
US8378777B2 (en) | 2008-07-29 | 2013-02-19 | Cooper Technologies Company | Magnetic electrical device |
US8310332B2 (en) * | 2008-10-08 | 2012-11-13 | Cooper Technologies Company | High current amorphous powder core inductor |
US8941457B2 (en) * | 2006-09-12 | 2015-01-27 | Cooper Technologies Company | Miniature power inductor and methods of manufacture |
US9589716B2 (en) | 2006-09-12 | 2017-03-07 | Cooper Technologies Company | Laminated magnetic component and manufacture with soft magnetic powder polymer composite sheets |
US8466764B2 (en) | 2006-09-12 | 2013-06-18 | Cooper Technologies Company | Low profile layered coil and cores for magnetic components |
US7791445B2 (en) * | 2006-09-12 | 2010-09-07 | Cooper Technologies Company | Low profile layered coil and cores for magnetic components |
US8279037B2 (en) * | 2008-07-11 | 2012-10-02 | Cooper Technologies Company | Magnetic components and methods of manufacturing the same |
US9558881B2 (en) | 2008-07-11 | 2017-01-31 | Cooper Technologies Company | High current power inductor |
US9859043B2 (en) | 2008-07-11 | 2018-01-02 | Cooper Technologies Company | Magnetic components and methods of manufacturing the same |
US8659379B2 (en) | 2008-07-11 | 2014-02-25 | Cooper Technologies Company | Magnetic components and methods of manufacturing the same |
US10192162B2 (en) * | 2015-05-21 | 2019-01-29 | Google Llc | Vector computation unit in a neural network processor |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB923251A (en) * | 1958-05-06 | 1963-04-10 | Bailey Meters Controls Ltd | Improvements in calculating networks |
US3691400A (en) * | 1967-12-13 | 1972-09-12 | Ltv Aerospace Corp | Unijunction transistor artificial neuron |
Family Cites Families (39)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US2065280A (en) * | 1933-05-13 | 1936-12-22 | Koros Ladislaus | Arrangement for deriving currents |
US2538500A (en) * | 1945-09-19 | 1951-01-16 | Bess Leon | Coincidence circuit |
US2712065A (en) * | 1951-08-30 | 1955-06-28 | Robert D Elbourn | Gate circuitry for electronic computers |
US2785305A (en) * | 1952-06-28 | 1957-03-12 | Rca Corp | Signal responsive circuit |
US2798156A (en) * | 1953-12-17 | 1957-07-02 | Burroughs Corp | Digit pulse counter |
US2901605A (en) * | 1953-12-18 | 1959-08-25 | Electronique & Automatisme Sa | Improvements in/or relating to electric pulse reshaping circuits |
CA608373A (en) * | 1954-06-08 | 1960-11-08 | George F. Pittman, Jr. | Control apparatus |
US2943791A (en) * | 1954-12-28 | 1960-07-05 | Ibm | Binary adder using transformer logical circuits |
GB827658A (en) * | 1955-04-25 | 1960-02-10 | Eiichi Goto | Improvements in or relating to electric multiplication circuits |
DE1074298B (en) * | 1955-08-15 | 1960-01-28 | Sperry Rand Corporation, New York, N. Y. (V. St. A.) | Logical circuit with controllable magnetic transformers |
US2820897A (en) * | 1955-08-29 | 1958-01-21 | Control Company Inc Comp | Universal gating package |
BE558700A (en) * | 1956-06-28 | |||
US2941722A (en) * | 1956-08-07 | 1960-06-21 | Roland L Van Allen | Single quadrant analogue computing means |
US2808990A (en) * | 1956-10-31 | 1957-10-08 | Roland L Van Allen | Polarity responsive voltage computing means |
US2934271A (en) * | 1957-01-28 | 1960-04-26 | Honeywell Regulator Co | Adding and subtracting apparatus |
GB896413A (en) * | 1957-08-21 | 1962-05-16 | Emi Ltd | Improvements relating to serial adding circuits |
US3021440A (en) * | 1959-12-31 | 1962-02-13 | Ibm | Cryogenic circuit with output threshold varied by input current |
US3250918A (en) * | 1961-08-28 | 1966-05-10 | Rca Corp | Electrical neuron circuits |
US3247366A (en) * | 1962-05-22 | 1966-04-19 | Gen Electric | Four-quadrant multiplier |
GB1089541A (en) * | 1963-04-11 | 1967-11-01 | English Electric Co Ltd | Logical electric circuits |
US3351773A (en) * | 1963-05-31 | 1967-11-07 | Mc Donnell Douglas Corp | Electronic circuit for simulating certain characteristics of a biological neuron |
DE1251379B (en) * | 1963-12-06 | 1967-10-05 | Radio Corporation oi America, New York NY (V St A) | Inductive cryotron switch |
US3383500A (en) * | 1965-03-24 | 1968-05-14 | Gen Magnetics Inc | Analog computer circuits for multiplying, dividing and root-taking with magnetic amplifier in a feed-back loop |
US3571918A (en) * | 1969-03-28 | 1971-03-23 | Texas Instruments Inc | Integrated circuits and fabrication thereof |
US3765082A (en) * | 1972-09-20 | 1973-10-16 | San Fernando Electric Mfg | Method of making an inductor chip |
JPS54182848U (en) * | 1978-06-16 | 1979-12-25 | ||
GB2045540B (en) * | 1978-12-28 | 1983-08-03 | Tdk Electronics Co Ltd | Electrical inductive device |
JPS59189212U (en) * | 1983-05-18 | 1984-12-15 | 株式会社村田製作所 | chip type inductor |
FR2558315B1 (en) * | 1984-01-16 | 1986-06-06 | Dassault Electronique | ELECTRONIC PULSE AMPLIFIER DEVICE, IN PARTICULAR FOR HIGH VOLTAGE OUTPUT |
US4660166A (en) * | 1985-01-22 | 1987-04-21 | Bell Telephone Laboratories, Incorporated | Electronic network for collective decision based on large number of connections between signals |
JPH0634236B2 (en) * | 1985-11-02 | 1994-05-02 | 日本放送協会 | Hierarchical information processing method |
US4719591A (en) * | 1985-11-07 | 1988-01-12 | American Telephone And Telegraph Company, At&T Bell Labs. | Optimization network for the decomposition of signals |
US4731747A (en) * | 1986-04-14 | 1988-03-15 | American Telephone And Telegraph Company, At&T Bell Laboratories | Highly parallel computation network with normalized speed of response |
US4771247A (en) * | 1987-09-24 | 1988-09-13 | General Electric Company | MMIC (monolithic microwave integrated circuit) low noise amplifier |
US4941122A (en) * | 1989-01-12 | 1990-07-10 | Recognition Equipment Incorp. | Neural network image processing system |
US5195171A (en) * | 1989-04-05 | 1993-03-16 | Yozan, Inc. | Data processing system |
US5553196A (en) * | 1989-04-05 | 1996-09-03 | Yozan, Inc. | Method for processing data using a neural network having a number of layers equal to an abstraction degree of the pattern to be processed |
JP2940933B2 (en) * | 1989-05-20 | 1999-08-25 | 株式会社リコー | Pattern recognition method |
US5371835A (en) * | 1990-02-02 | 1994-12-06 | Kabushikikaisha Wacom | Inductively coupled neural network |
-
1990
- 1990-07-06 EP EP19900112956 patent/EP0411341A3/en not_active Withdrawn
- 1990-07-09 US US07/549,748 patent/US5463717A/en not_active Expired - Fee Related
- 1990-07-10 KR KR1019900010403A patent/KR910003516A/en active IP Right Grant
-
1995
- 1995-05-23 US US08/447,775 patent/US5664069A/en not_active Expired - Fee Related
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB923251A (en) * | 1958-05-06 | 1963-04-10 | Bailey Meters Controls Ltd | Improvements in calculating networks |
US3691400A (en) * | 1967-12-13 | 1972-09-12 | Ltv Aerospace Corp | Unijunction transistor artificial neuron |
Non-Patent Citations (8)
Title |
---|
ARCHIV FUR TECHNISCHES MESSEN UND INDUSTRIELLE MESSTECHNIK no. 375, April 1967, MUNCHEN, DE pages 37 - 41; I. HORVAT ET AL.: "Genaue potentialfreie summierung der messwerte eines fernmess-systems mittels des zerhackerverfahrens", page 37, right-hand column, line 17 - page 38, left-hand column, line 23; figure 2. * |
AUTOMATIC CONTROL vol. 17, no. 3, October 1962, NEW YORK, US pages 16 - 19; N. SUSSMAN: "Magnetic modulators: characteristics and applications", page 19, line 18 - line 26; figure 8. * |
COMPUTER, vol. 21, no. 3, March 1988, LONG BEACH, US pages 52 - 63; J.HUTCHINSON, "Computing motion using analog and binary resistive networks", page 61, left-hand column, line 34 - line 46; figure 8. * |
COMPUTER, vol. 21, no. 3, March 1988, pages 52-63, Long Beach, US; J. HUTCHINSON: "Computing motion using analog and binary resistive networks" * |
IEEE ACOUSTICS, SPEECH, AND SIGNAL PROCESSING MAGAZINE. April 1987, NEW YORK US pages 4 - 21; R.P. LIPPMANN: "An introduction to computing with neural nets", page 15, right column, line 34 - page 16, right-hand column, line 47; figures 14,15. * |
IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS vol. 2 OF3, May 1989 PORTLAND, US pages 774 - 777; F.Y SHIH ET AL: "Image morphological operations by neural circuits", page 774, left-hand column, line 1 - page 777, line 14; figures 3-6. * |
IEEE TRANSACTIONS ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING. vol. 36, no. 7, July 1988, NEW YORK US pages 1180 - 1190; VIDAL: "Implementing neural nets with programmable logic", page 1184, rigth-hand column, line 35 - line 55; figure3. * |
NEURAL NETWORKS vol. 1, no. 2, 1988, ELMSFORD, US pages 119 - 130; K. FUKUSHIMA: "Neocognitron : a hierarchical neural network capable of visual pattern recognition", page 123, right-hand column, line 8 - page 124, left-hand column, line 6; figure 6. * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5371835A (en) * | 1990-02-02 | 1994-12-06 | Kabushikikaisha Wacom | Inductively coupled neural network |
EP0443208A2 (en) * | 1990-02-20 | 1991-08-28 | Kabushiki Kaisha Wacom | Inductively coupled neural network |
EP0443208A3 (en) * | 1990-02-20 | 1991-10-16 | Kabushiki Kaisha Wacom | Inductively coupled neural network |
US5297232A (en) * | 1991-10-30 | 1994-03-22 | Westinghouse Electric Corp. | Wireless neural network and a wireless neural processing element |
Also Published As
Publication number | Publication date |
---|---|
US5463717A (en) | 1995-10-31 |
EP0411341A3 (en) | 1992-05-13 |
KR910003516A (en) | 1991-02-27 |
US5664069A (en) | 1997-09-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP0411341A2 (en) | Neural network | |
Kwan et al. | A fuzzy neural network and its application to pattern recognition | |
Hussain et al. | A novel feature recognition neural network and its application to character recognition | |
Michalski | A planar geometrical model for representing multi-dimensional discrete spaces and multiple-valued logic functions | |
EP0459276A2 (en) | Data processing system | |
US5148045A (en) | Apparatus and method for assigning a plurality of elements to a plurality of cells | |
US5361328A (en) | Data processing system using a neural network | |
Chakraborty | Feature subset selection by neuro-rough hybridization | |
JPH06111038A (en) | Neural network and operating method thereof | |
CN1526077A (en) | Digital system and a method for error detection thereof | |
EP0420254B1 (en) | Data processing system | |
Schmid et al. | Hardware realization of a Hamming neural network with on-chip learning | |
JPH08329032A (en) | Neural net type pattern recognition device and learning method for neural net | |
Lin et al. | Design of k-WTA/sorting network using maskable WTA/MAX circuit | |
Watta et al. | Decoupled-voting hamming associative memory networks | |
Yamakawa | Silicon implementation of a fuzzy neuron | |
CN113673272B (en) | Double-layer labeling two-stage cascade calculation loss value method based on pet detection | |
Wu et al. | Automatically generated rules and membership functions for a neural fuzzy-based fault classifier | |
Park | An ART2 trained by two-stage learning on circularly ordered data sequence | |
Nishida et al. | An analysis of a multi-layered competitive net for invariant pattern recognition | |
Hayashi et al. | Model reduction of neural network trees based on dimensionality reduction | |
Mishra | Self organizing fuzzy neural network: an application to character recognition | |
Dandgaval et al. | A Review on Object Detection Techniques using Deep Learning | |
Sung et al. | Optimal synthesis method for binary neural network using NETLA | |
JP3804088B2 (en) | Character recognition device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
AK | Designated contracting states |
Kind code of ref document: A2 Designated state(s): BE DE FR GB IT NL SE |
|
17P | Request for examination filed |
Effective date: 19911204 |
|
PUAL | Search report despatched |
Free format text: ORIGINAL CODE: 0009013 |
|
AK | Designated contracting states |
Kind code of ref document: A3 Designated state(s): BE DE FR GB IT NL SE |
|
RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: YOZAN INC. Owner name: SHARP KABUSHIKI KAISHA |
|
17Q | First examination report despatched |
Effective date: 19950127 |
|
GRAG | Despatch of communication of intention to grant |
Free format text: ORIGINAL CODE: EPIDOS AGRA |
|
GRAG | Despatch of communication of intention to grant |
Free format text: ORIGINAL CODE: EPIDOS AGRA |
|
GRAH | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOS IGRA |
|
GRAH | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOS IGRA |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN |
|
18D | Application deemed to be withdrawn |
Effective date: 19990202 |